public interface UProperty
Selection constants for Unicode properties.
These constants are used in functions like UCharacter.hasBinaryProperty(int) to select one of the Unicode properties.
The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
For details about the properties see UAX #44: Unicode Character Database.
Important: If ICU is built with UCD files from Unicode versions below 3.2, then properties marked with "new" are not or not fully available. Check UCharacter.getUnicodeVersion() to be sure.
UCharacter
Modifier and Type | Interface and Description |
---|---|
static interface |
UProperty.NameChoice
Selector constants for UCharacter.getPropertyName() and
UCharacter.getPropertyValueName().
|
Modifier and Type | Field and Description |
---|---|
static int |
AGE
String property Age.
|
static int |
ALPHABETIC
Binary property Alphabetic.
|
static int |
ASCII_HEX_DIGIT
Binary property ASCII_Hex_Digit (0-9 A-F a-f).
|
static int |
BASIC_EMOJI
Binary property of strings Basic_Emoji.
|
static int |
BIDI_CLASS
Enumerated property Bidi_Class.
|
static int |
BIDI_CONTROL
Binary property Bidi_Control.
|
static int |
BIDI_MIRRORED
Binary property Bidi_Mirrored.
|
static int |
BIDI_MIRRORING_GLYPH
String property Bidi_Mirroring_Glyph.
|
static int |
BIDI_PAIRED_BRACKET
String property Bidi_Paired_Bracket (new in Unicode 6.3).
|
static int |
BIDI_PAIRED_BRACKET_TYPE
Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3).
|
static int |
BINARY_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
BINARY_START
First constant for binary Unicode properties.
|
static int |
BLOCK
Enumerated property Block.
|
static int |
CANONICAL_COMBINING_CLASS
Enumerated property Canonical_Combining_Class.
|
static int |
CASE_FOLDING
String property Case_Folding.
|
static int |
CASE_IGNORABLE
Binary property Case_Ignorable.
|
static int |
CASE_SENSITIVE
Binary property Case_Sensitive.
|
static int |
CASED
Binary property Cased.
|
static int |
CHANGES_WHEN_CASEFOLDED
Binary property Changes_When_Casefolded.
|
static int |
CHANGES_WHEN_CASEMAPPED
Binary property Changes_When_Casemapped.
|
static int |
CHANGES_WHEN_LOWERCASED
Binary property Changes_When_Lowercased.
|
static int |
CHANGES_WHEN_NFKC_CASEFOLDED
Binary property Changes_When_NFKC_Casefolded.
|
static int |
CHANGES_WHEN_TITLECASED
Binary property Changes_When_Titlecased.
|
static int |
CHANGES_WHEN_UPPERCASED
Binary property Changes_When_Uppercased.
|
static int |
DASH
Binary property Dash.
|
static int |
DECOMPOSITION_TYPE
Enumerated property Decomposition_Type.
|
static int |
DEFAULT_IGNORABLE_CODE_POINT
Binary property Default_Ignorable_Code_Point (new).
|
static int |
DEPRECATED
Binary property Deprecated (new).
|
static int |
DIACRITIC
Binary property Diacritic.
|
static int |
DOUBLE_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
DOUBLE_START
First constant for double Unicode properties.
|
static int |
EAST_ASIAN_WIDTH
Enumerated property East_Asian_Width.
|
static int |
EMOJI
Binary property Emoji.
|
static int |
EMOJI_COMPONENT
Binary property Emoji_Component.
|
static int |
EMOJI_KEYCAP_SEQUENCE
Binary property of strings Emoji_Keycap_Sequence.
|
static int |
EMOJI_MODIFIER
Binary property Emoji_Modifier.
|
static int |
EMOJI_MODIFIER_BASE
Binary property Emoji_Modifier_Base.
|
static int |
EMOJI_PRESENTATION
Binary property Emoji_Presentation.
|
static int |
EXTENDED_PICTOGRAPHIC
Binary property Extended_Pictographic.
|
static int |
EXTENDER
Binary property Extender.
|
static int |
FULL_COMPOSITION_EXCLUSION
Binary property Full_Composition_Exclusion.
|
static int |
GENERAL_CATEGORY
Enumerated property General_Category.
|
static int |
GENERAL_CATEGORY_MASK
Bitmask property General_Category_Mask.
|
static int |
GRAPHEME_BASE
Binary property Grapheme_Base (new).
|
static int |
GRAPHEME_CLUSTER_BREAK
Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
|
static int |
GRAPHEME_EXTEND
Binary property Grapheme_Extend (new).
|
static int |
GRAPHEME_LINK
Binary property Grapheme_Link (new).
|
static int |
HANGUL_SYLLABLE_TYPE
Enumerated property Hangul_Syllable_Type, new in Unicode 4.
|
static int |
HEX_DIGIT
Binary property Hex_Digit.
|
static int |
HYPHEN
Binary property Hyphen.
|
static int |
ID_COMPAT_MATH_CONTINUE
Binary property ID_Compat_Math_Continue.
|
static int |
ID_COMPAT_MATH_START
Binary property ID_Compat_Math_Start.
|
static int |
ID_CONTINUE
Binary property ID_Continue.
|
static int |
ID_START
Binary property ID_Start.
|
static int |
IDENTIFIER_STATUS
Enumerated property Identifier_Status.
|
static int |
IDENTIFIER_TYPE
Miscellaneous property Identifier_Type.
|
static int |
IDEOGRAPHIC
Binary property Ideographic.
|
static int |
IDS_BINARY_OPERATOR
Binary property IDS_Binary_Operator (new).
|
static int |
IDS_TRINARY_OPERATOR
Binary property IDS_Trinary_Operator (new).
|
static int |
IDS_UNARY_OPERATOR
Binary property IDS_Unary_Operator.
|
static int |
INDIC_CONJUNCT_BREAK
Enumerated property Indic_Conjunct_Break.
|
static int |
INDIC_POSITIONAL_CATEGORY
Enumerated property Indic_Positional_Category.
|
static int |
INDIC_SYLLABIC_CATEGORY
Enumerated property Indic_Syllabic_Category.
|
static int |
INT_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
INT_START
First constant for enumerated/integer Unicode properties.
|
static int |
ISO_COMMENT
Deprecated.
ICU 49
|
static int |
JOIN_CONTROL
Binary property Join_Control.
|
static int |
JOINING_GROUP
Enumerated property Joining_Group.
|
static int |
JOINING_TYPE
Enumerated property Joining_Type.
|
static int |
LEAD_CANONICAL_COMBINING_CLASS
Enumerated property Lead_Canonical_Combining_Class.
|
static int |
LINE_BREAK
Enumerated property Line_Break.
|
static int |
LOGICAL_ORDER_EXCEPTION
Binary property Logical_Order_Exception (new).
|
static int |
LOWERCASE
Binary property Lowercase.
|
static int |
LOWERCASE_MAPPING
String property Lowercase_Mapping.
|
static int |
MASK_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
MASK_START
First constant for bit-mask Unicode properties.
|
static int |
MATH
Binary property Math.
|
static int |
MODIFIER_COMBINING_MARK
Binary property Modifier_Combining_Mark.
|
static int |
NAME
String property Name.
|
static int |
NFC_INERT
Binary property NFC_Inert.
|
static int |
NFC_QUICK_CHECK
Enumerated property NFC_Quick_Check.
|
static int |
NFD_INERT
Binary property NFD_Inert.
|
static int |
NFD_QUICK_CHECK
Enumerated property NFD_Quick_Check.
|
static int |
NFKC_INERT
Binary property NFKC_Inert.
|
static int |
NFKC_QUICK_CHECK
Enumerated property NFKC_Quick_Check.
|
static int |
NFKD_INERT
Binary property NFKD_Inert.
|
static int |
NFKD_QUICK_CHECK
Enumerated property NFKD_Quick_Check.
|
static int |
NONCHARACTER_CODE_POINT
Binary property Noncharacter_Code_Point.
|
static int |
NUMERIC_TYPE
Enumerated property Numeric_Type.
|
static int |
NUMERIC_VALUE
Double property Numeric_Value.
|
static int |
OTHER_PROPERTY_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
OTHER_PROPERTY_START
First constant for Unicode properties with unusual value types.
|
static int |
PATTERN_SYNTAX
Binary property Pattern_Syntax (new in Unicode 4.1).
|
static int |
PATTERN_WHITE_SPACE
Binary property Pattern_White_Space (new in Unicode 4.1).
|
static int |
POSIX_ALNUM
Binary property alnum (a C/POSIX character class).
|
static int |
POSIX_BLANK
Binary property blank (a C/POSIX character class).
|
static int |
POSIX_GRAPH
Binary property graph (a C/POSIX character class).
|
static int |
POSIX_PRINT
Binary property print (a C/POSIX character class).
|
static int |
POSIX_XDIGIT
Binary property xdigit (a C/POSIX character class).
|
static int |
PREPENDED_CONCATENATION_MARK
Binary property Prepended_Concatenation_Mark.
|
static int |
QUOTATION_MARK
Binary property Quotation_Mark.
|
static int |
RADICAL
Binary property Radical (new).
|
static int |
REGIONAL_INDICATOR
Binary property Regional_Indicator.
|
static int |
RGI_EMOJI
Binary property of strings RGI_Emoji.
|
static int |
RGI_EMOJI_FLAG_SEQUENCE
Binary property of strings RGI_Emoji_Flag_Sequence.
|
static int |
RGI_EMOJI_MODIFIER_SEQUENCE
Binary property of strings RGI_Emoji_Modifier_Sequence.
|
static int |
RGI_EMOJI_TAG_SEQUENCE
Binary property of strings RGI_Emoji_Tag_Sequence.
|
static int |
RGI_EMOJI_ZWJ_SEQUENCE
Binary property of strings RGI_Emoji_ZWJ_Sequence.
|
static int |
S_TERM
Binary property STerm (new in Unicode 4.0.1).
|
static int |
SCRIPT
Enumerated property Script.
|
static int |
SCRIPT_EXTENSIONS
Miscellaneous property Script_Extensions (new in Unicode 6.0).
|
static int |
SEGMENT_STARTER
Binary Property Segment_Starter.
|
static int |
SENTENCE_BREAK
Enumerated property Sentence_Break (new in Unicode 4.1).
|
static int |
SIMPLE_CASE_FOLDING
String property Simple_Case_Folding.
|
static int |
SIMPLE_LOWERCASE_MAPPING
String property Simple_Lowercase_Mapping.
|
static int |
SIMPLE_TITLECASE_MAPPING
String property Simple_Titlecase_Mapping.
|
static int |
SIMPLE_UPPERCASE_MAPPING
String property Simple_Uppercase_Mapping.
|
static int |
SOFT_DOTTED
Binary property Soft_Dotted (new).
|
static int |
STRING_LIMIT
Deprecated.
ICU 58 The numeric value may change over time, see ICU ticket #12420.
|
static int |
STRING_START
First constant for string Unicode properties.
|
static int |
TERMINAL_PUNCTUATION
Binary property Terminal_Punctuation.
|
static int |
TITLECASE_MAPPING
String property Titlecase_Mapping.
|
static int |
TRAIL_CANONICAL_COMBINING_CLASS
Enumerated property Trail_Canonical_Combining_Class.
|
static int |
UNDEFINED
Deprecated.
This API is ICU internal only.
|
static int |
UNICODE_1_NAME
Deprecated.
ICU 49
|
static int |
UNIFIED_IDEOGRAPH
Binary property Unified_Ideograph (new).
|
static int |
UPPERCASE
Binary property Uppercase.
|
static int |
UPPERCASE_MAPPING
String property Uppercase_Mapping.
|
static int |
VARIATION_SELECTOR
Binary property Variation_Selector (new in Unicode 4.0.1).
|
static int |
VERTICAL_ORIENTATION
Enumerated property Vertical_Orientation.
|
static int |
WHITE_SPACE
Binary property White_Space.
|
static int |
WORD_BREAK
Enumerated property Word_Break (new in Unicode 4.1).
|
static int |
XID_CONTINUE
Binary property XID_Continue.
|
static int |
XID_START
Binary property XID_Start.
|
@Deprecated static final int UNDEFINED
static final int ALPHABETIC
Binary property Alphabetic.
Property for UCharacter.isUAlphabetic(), different from the property in UCharacter.isalpha().
Lu + Ll + Lt + Lm + Lo + Nl + Other_Alphabetic.
static final int BINARY_START
static final int ASCII_HEX_DIGIT
static final int BIDI_CONTROL
Binary property Bidi_Control.
Format controls which have specific functions in the Bidi Algorithm.
static final int BIDI_MIRRORED
Binary property Bidi_Mirrored.
Characters that may change display in RTL text.
Property for UCharacter.isMirrored().
See Bidi Algorithm; UTR 9.
static final int DASH
Binary property Dash.
Variations of dashes.
static final int DEFAULT_IGNORABLE_CODE_POINT
Binary property Default_Ignorable_Code_Point (new).
Property that indicates codepoint is ignorable in most processing.
Codepoints (2060..206F, FFF0..FFFB, E0000..E0FFF) + Other_Default_Ignorable_Code_Point + (Cf + Cc + Cs - White_Space)
static final int DEPRECATED
Binary property Deprecated (new).
The usage of deprecated characters is strongly discouraged.
static final int DIACRITIC
Binary property Diacritic.
Characters that linguistically modify the meaning of another character to which they apply.
static final int EXTENDER
Binary property Extender.
Extend the value or shape of a preceding alphabetic character, e.g. length and iteration marks.
static final int FULL_COMPOSITION_EXCLUSION
Binary property Full_Composition_Exclusion.
CompositionExclusions.txt + Singleton Decompositions + Non-Starter Decompositions.
static final int GRAPHEME_BASE
Binary property Grapheme_Base (new).
For programmatic determination of grapheme cluster boundaries. [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ
static final int GRAPHEME_EXTEND
Binary property Grapheme_Extend (new).
For programmatic determination of grapheme cluster boundaries.
Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ
static final int GRAPHEME_LINK
Binary property Grapheme_Link (new).
For programmatic determination of grapheme cluster boundaries.
static final int HEX_DIGIT
Binary property Hex_Digit.
Characters commonly used for hexadecimal numbers.
static final int HYPHEN
Binary property Hyphen.
Dashes used to mark connections between pieces of words, plus the Katakana middle dot.
static final int ID_CONTINUE
Binary property ID_Continue.
Characters that can continue an identifier.
ID_Start+Mn+Mc+Nd+Pc
static final int ID_START
Binary property ID_Start.
Characters that can start an identifier.
Lu+Ll+Lt+Lm+Lo+Nl
static final int IDEOGRAPHIC
Binary property Ideographic.
CJKV ideographs.
static final int IDS_BINARY_OPERATOR
Binary property IDS_Binary_Operator (new).
For programmatic determination of Ideographic Description Sequences.
static final int IDS_TRINARY_OPERATOR
Binary property IDS_Trinary_Operator (new).
For programmatic determination of Ideographic Description Sequences.
static final int JOIN_CONTROL
Binary property Join_Control.
Format controls for cursive joining and ligation.
static final int LOGICAL_ORDER_EXCEPTION
Binary property Logical_Order_Exception (new).
Characters that do not use logical order and require special handling in most processing.
static final int LOWERCASE
Binary property Lowercase.
Same as UCharacter.isULowercase(), different from UCharacter.islower().
Ll+Other_Lowercase
static final int MATH
Binary property Math.
Sm+Other_Math
static final int NONCHARACTER_CODE_POINT
Binary property Noncharacter_Code_Point.
Code points that are explicitly defined as illegal for the encoding of characters.
static final int QUOTATION_MARK
Binary property Quotation_Mark.
static final int RADICAL
Binary property Radical (new).
For programmatic determination of Ideographic Description Sequences.
static final int SOFT_DOTTED
Binary property Soft_Dotted (new).
Characters with a "soft dot", like i or j.
An accent placed on these characters causes the dot to disappear.
static final int TERMINAL_PUNCTUATION
Binary property Terminal_Punctuation.
Punctuation characters that generally mark the end of textual units.
static final int UNIFIED_IDEOGRAPH
Binary property Unified_Ideograph (new).
For programmatic determination of Ideographic Description Sequences.
static final int UPPERCASE
Binary property Uppercase.
Same as UCharacter.isUUppercase(), different from UCharacter.isUpperCase().
Lu+Other_Uppercase
static final int WHITE_SPACE
Binary property White_Space.
Same as UCharacter.isUWhiteSpace(), different from UCharacter.isSpace() and UCharacter.isWhitespace(). Space characters+TAB+CR+LF-ZWSP-ZWNBSP
static final int XID_CONTINUE
Binary property XID_Continue.
ID_Continue modified to allow closure under normalization forms NFKC and NFKD.
static final int XID_START
Binary property XID_Start.
ID_Start modified to allow closure under normalization forms NFKC and NFKD.
static final int CASE_SENSITIVE
Binary property Case_Sensitive.
Either the source of a case mapping or in the target of a case mapping. Not the same as the general category Cased_Letter.
static final int S_TERM
static final int VARIATION_SELECTOR
static final int NFD_INERT
static final int NFKD_INERT
NFD_INERT
,
Constant Field Valuesstatic final int NFC_INERT
NFD_INERT
,
Constant Field Valuesstatic final int NFKC_INERT
NFD_INERT
,
Constant Field Valuesstatic final int SEGMENT_STARTER
static final int PATTERN_SYNTAX
static final int PATTERN_WHITE_SPACE
static final int POSIX_ALNUM
static final int POSIX_BLANK
static final int POSIX_GRAPH
static final int POSIX_PRINT
static final int POSIX_XDIGIT
static final int CASED
static final int CASE_IGNORABLE
static final int CHANGES_WHEN_LOWERCASED
static final int CHANGES_WHEN_UPPERCASED
static final int CHANGES_WHEN_TITLECASED
static final int CHANGES_WHEN_CASEFOLDED
static final int CHANGES_WHEN_CASEMAPPED
static final int CHANGES_WHEN_NFKC_CASEFOLDED
static final int EMOJI
static final int EMOJI_PRESENTATION
static final int EMOJI_MODIFIER
static final int EMOJI_MODIFIER_BASE
static final int EMOJI_COMPONENT
static final int REGIONAL_INDICATOR
static final int PREPENDED_CONCATENATION_MARK
static final int EXTENDED_PICTOGRAPHIC
static final int BASIC_EMOJI
static final int EMOJI_KEYCAP_SEQUENCE
static final int RGI_EMOJI_MODIFIER_SEQUENCE
static final int RGI_EMOJI_FLAG_SEQUENCE
static final int RGI_EMOJI_TAG_SEQUENCE
static final int RGI_EMOJI_ZWJ_SEQUENCE
static final int RGI_EMOJI
static final int IDS_UNARY_OPERATOR
static final int ID_COMPAT_MATH_START
Used in mathematical identifier profile in UAX #31.
static final int ID_COMPAT_MATH_CONTINUE
Used in mathematical identifier profile in UAX #31.
static final int MODIFIER_COMBINING_MARK
Used by the AMTRA algorithm in UAX #53.
@Deprecated static final int BINARY_LIMIT
static final int BIDI_CLASS
static final int INT_START
static final int BLOCK
static final int CANONICAL_COMBINING_CLASS
static final int DECOMPOSITION_TYPE
static final int EAST_ASIAN_WIDTH
static final int GENERAL_CATEGORY
static final int JOINING_GROUP
static final int JOINING_TYPE
static final int LINE_BREAK
static final int NUMERIC_TYPE
static final int SCRIPT
static final int HANGUL_SYLLABLE_TYPE
static final int NFD_QUICK_CHECK
static final int NFKD_QUICK_CHECK
static final int NFC_QUICK_CHECK
static final int NFKC_QUICK_CHECK
static final int LEAD_CANONICAL_COMBINING_CLASS
static final int TRAIL_CANONICAL_COMBINING_CLASS
static final int GRAPHEME_CLUSTER_BREAK
static final int SENTENCE_BREAK
static final int WORD_BREAK
static final int BIDI_PAIRED_BRACKET_TYPE
static final int INDIC_POSITIONAL_CATEGORY
static final int INDIC_SYLLABIC_CATEGORY
static final int VERTICAL_ORIENTATION
static final int IDENTIFIER_STATUS
static final int INDIC_CONJUNCT_BREAK
@Deprecated static final int INT_LIMIT
static final int GENERAL_CATEGORY_MASK
static final int MASK_START
@Deprecated static final int MASK_LIMIT
static final int NUMERIC_VALUE
static final int DOUBLE_START
@Deprecated static final int DOUBLE_LIMIT
static final int AGE
static final int STRING_START
static final int BIDI_MIRRORING_GLYPH
static final int CASE_FOLDING
@Deprecated static final int ISO_COMMENT
static final int LOWERCASE_MAPPING
static final int NAME
static final int SIMPLE_CASE_FOLDING
static final int SIMPLE_LOWERCASE_MAPPING
static final int SIMPLE_TITLECASE_MAPPING
static final int SIMPLE_UPPERCASE_MAPPING
static final int TITLECASE_MAPPING
@Deprecated static final int UNICODE_1_NAME
static final int UPPERCASE_MAPPING
static final int BIDI_PAIRED_BRACKET
@Deprecated static final int STRING_LIMIT
static final int SCRIPT_EXTENSIONS
static final int OTHER_PROPERTY_START
static final int IDENTIFIER_TYPE
Corresponds to UCharacter.hasIdentifierType(int, UCharacter.IdentifierType)
and
UCharacter.getIdentifierTypes(int, java.util.EnumSet)
.
Each code point maps to a set of IdentifierType values.
UCharacter.hasIdentifierType(int, UCharacter.IdentifierType)
,
UCharacter.getIdentifierTypes(int, java.util.EnumSet)
,
Constant Field Values@Deprecated static final int OTHER_PROPERTY_LIMIT
Copyright © 2016 Unicode, Inc. and others.